© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116016
    Prev
    Next
    INDEX
    Explanations

    list item prefixes

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects mentions of legal or judicial reporting—names, courts, judgments, and related legal actions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ghana
    -0.93
     Filipinos
    -0.88
    ærk
    -0.85
     eki
    -0.85
    sians
    -0.85
     Zimbabwe
    -0.85
    keySet
    -0.84
     Olímpicos
    -0.83
    Iran
    -0.82
     Africans
    -0.82
    POSITIVE LOGITS
     Alkal
    0.96
     Arqu
    0.90
    閉じ
    0.88
    northern
    0.82
     nomadic
    0.81
    膨胀
    0.81
     Noma
    0.79
    miniature
    0.79
    手間
    0.78
    EFIAPI
    0.77
    Activations Density 0.006%

    No Known Activations